GMP 2024| Keynote Talk Preview

GMP 2024 Keynote Talk

 Leif Kobbelt

 RWTH Aachen University, Germany

Abstract:

  Many tasks in the analysis and synthesis of (collections of) 3D shapes boil down to computing a map between two surfaces. Such inter-surface maps can be used to establish correspondences, to transfer information or annotation from one object to another, or to plausibly deform one shape into another. If the two shapes are represented as polygon meshes, a continuous inter-surface map does not only assign the vertices of the source mesh to the target mesh but also maps the interior of the triangles which adds to the complexity of the task. The goal is to find a map with minimized distortion that in addition satisfies a number of constraints such as prescribed landmark correspondences. The emerging optimization problem has a continuous geometric "distortion minimization" aspect but when it comes to objects with non-zero genus, it also has a discrete topological "handle matching" aspect. In this talk I will report on some of our recent findings and methods to effectively and efficiently address both aspects when computing optimal inter-surface maps.

Title:  Inter-Surface Maps

Bio:  

  Leif Kobbelt received a PhD degree from Karlsruhe Institute of Technology in 1994. He worked at the University of Wisconsin in Madison, University of Erlangen-Nuremberg, and the Max Planck Institute of Computer Science before he moved to RWTH Aachen University in 2001. At RWTH he is a distinguished professor of Computer Science and head of the Institute for Computer Graphics and Multimedia. His major research interests include 3D reconstruction and efficient geometry processing. Since 2003 he is coordinating the Symposium on Geometry Processing conference series. He received a number of academic awards including an ERC Advanced Grant in 2013 and the Gottfried Wilhelm Leibniz Prize in 2014. He has been named a fellow of the Eurographics Association (2008) as well as a distinguished professor (2013) and a fellow (2019) of RWTH Aachen University. In 2015, he became a member of the Academia Europaea and in 2016 a member of the North Rhine Westphalian Academy of Sciences.

Webpage:  

https://www.graphics.rwth-aachen.de

Xin (Shane) Li

Texas A&M University, USA

Abstract:

  Recent advancements in generative AI have unlocked exciting new prospects in the realm of geometric modeling and processing. They are poised to revolutionize 3D fields, like the impact they have made on images and computer vision. In this talk, I will share our recent explorations in utilizing diffusion models as a powerful tool to enhance 3D geometric modeling.  I will start with the discussion of modeling specific objects, such as human faces and human bodies. The construction and modeling of these subjects possess inherent priors yet require stringent geometric and semantic constraints. Then I will talk about the 3D surface generation for a broader range of objects, which enables flexible construction of high-resolution 3D models of arbitrary geometries and topologies using various user prompts such as texts, images, or sketches. 

Title:

Exploring New Frontiers of 3D Geometric Modeling with Generative AI and Diffusion Models

Bio:

  Xin Li is a Professor and Chair of the Section of Visual Computing and Interactive Media, School of Performance, Visualization, and Fine Arts, and a joint faculty member of Department of Computer Science and Engineering, at Texas A&M University. He got his B.S. degree in Computer Science at University of Science and Technology of China (USTC) in 2003, and Ph.D. in Computer Science from State University of New York at Stony Brook in 2008. From 2008 to 2022, he was a faculty member at School of Electrical Engineering and Computer Science, Louisiana State University. Xin Li is in the editorial boards for multiple journals including Computer-aided Design (CAD), Computer Aided Geometric Design (CAGD), and Journal of Computer Science and Technology (JCST), and so on. He served as a technical program co-chair for GMP 2022, Solid and Physical Modeling (SPM) 2019 and 2020, SIAM Geometric Design (GD) 2023, and as a Conference co-chair for SPM+GD 2021. His research areas are in visual computing, geometric modeling and processing, computer vision, and computer-aided design. He has published over 140 peer-reviewed journal/conference papers in these fields. Xin received IBM faculty award in 2011, and Solid Modeling Association Young Investigator Award in 2020. Recently, his research interest is in AI-enabled visual and geometric understanding, processing, and synthesis. 

Webpage: 

https://people.tamu.edu/~xinli/

Takeo Igarashi

The University of Tokyo, Japan

Abstract:

  Digital human is increasing popular in entertainment, advertisement, e-commerce, and education. Every digital human needs to be properly dressed, but it is not easy to design a garment and put it on a digital human. In this talk, I will introduce our work on interactive techniques to design and manipulate cloth and garments for digital and physical human. I will introduce projects such as manipulation of garments on a body, garment design supported by real-time cloth simulation, AR-based garment design, and virtual-try on using measurement garment and robotic manikin.

Title:

Dressing Digital Human: Interactive Techniques for Cloth and Garments

Bio:

  Takeo Igarashi is a professor at the Department of Creative Informatics, The University of Tokyo. He His research interest is in user interfaces and interactive computer graphics. He has received the ACM SIGGRAPH 2006 Significant New Researcher Award, CHI 2019 Academy Award, and ACM UIST 2019 Lasting Impact Award. He served as a program co-chair for UIST 2013, general co-chair for UIST 2016, technical papers chair for SIGGRAPH ASIA 2018, technical program co-chair for ACM CHI 2021, and conference chair for SIGGRAPH ASIA 2024.

Webpage:  

http://www-ui.is.s.u-tokyo.ac.jp/~takeo